{"text": "MinerU Popo是一個面向複雜文檔解析的後處理模型框架。核心目標是把OCR和版面分析得到的頁面集結果,進一步整理成文檔集結構化知識。它並非替代MinerU、Manty OCR或PaddleOCR等項目,而是在這些解析工具進行OCR之後,對標題層級,段落連續性、跨頁表格、圖文關係和閱讀順序進行統一推理與修復。通俗地說,OCR能力是負責把字看出來。MinerU Popo負責把整份文檔真正組織起來。在技術上,MinerU Popo採用4B參數後處理模型,並集合任務化數據引擎。動態分塊同步和文檔增強方法。重點解決長文檔在分翼、跨翼和複雜版式下容易出現的結構斷裂問題。在公開指標中,接入Popo框架後,MinerU的TEDS從53.7提升到90.6。MineQ-C2從48.9提升到87.4,說明它能夠顯著提升文檔結構恢復質量。它的價值在於讓知識庫、RAG智能問答、學術論文解析和企業文檔治理,獲得更乾淨、更穩定、更可計算的文檔資產。MinerU Popo讓複雜文檔從可識別,走向可理解、可治理、可計算。MinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU PopoMinerU Popo", "segments": [{"id": 0, "seek": 0, "start": 0.0, "end": 11.4, "text": "MinerU Popo是一個面向複雜文檔解析的後處理模型框架。核心目標是把OCR和版面分析得到的頁面集結果,進一步整理成文檔集結構化知識。", "tokens": [50365, 44, 4564, 52, 10215, 78, 1541, 8990, 8833, 24282, 164, 97, 229, 6306, 250, 17174, 40741, 242, 17278, 7360, 238, 1546, 5661, 39289, 13876, 41908, 39823, 21416, 228, 7360, 114, 1543, 8987, 116, 7945, 11386, 46299, 1541, 16075, 46, 18547, 12565, 42096, 8833, 6627, 7360, 238, 5916, 4511, 1546, 8313, 223, 8833, 26020, 35181, 11, 18214, 2257, 31429, 27662, 13876, 11336, 17174, 40741, 242, 26020, 17144, 43362, 23756, 6498, 43143, 1543, 50935], "temperature": 0, "avg_logprob": -0.15639057514830407, "compression_ratio": 1.1832298136645962, "no_speech_prob": 9.6452212536291e-12}, {"id": 1, "seek": 0, "start": 11.4, "end": 25.8, "text": "它並非替代MinerU、Manty OCR或PaddleOCR等項目,而是在這些解析工具進行OCR之後,對標題層級,段落連續性、跨頁表格、圖文關係和閱讀順序進行統一推理與修復。", "tokens": [50935, 11284, 35934, 12107, 9531, 123, 19105, 44, 4564, 52, 1231, 44, 394, 88, 422, 18547, 19780, 50112, 2285, 46, 18547, 10187, 8313, 227, 11386, 11, 11070, 1541, 3581, 29869, 17278, 7360, 238, 23323, 39806, 18214, 8082, 46, 18547, 26362, 11, 2855, 46299, 14475, 9636, 97, 35315, 11, 28427, 30848, 36252, 29583, 21686, 1231, 6563, 101, 8313, 223, 17571, 30921, 1231, 2523, 244, 17174, 25802, 12565, 29602, 7422, 222, 8313, 228, 6346, 237, 18214, 8082, 33725, 2257, 33597, 13876, 34127, 7792, 106, 2172, 102, 1543, 51655], "temperature": 0, "avg_logprob": -0.15639057514830407, "compression_ratio": 1.1832298136645962, "no_speech_prob": 9.6452212536291e-12}, {"id": 2, "seek": 2580, "start": 25.8, "end": 32.6, "text": "通俗地說,OCR能力是負責把字看出來。MinerU Popo負責把整份文檔真正組織起來。", "tokens": [50365, 19550, 7792, 245, 10928, 4622, 11, 46, 18547, 8225, 13486, 1541, 11561, 254, 11561, 105, 16075, 22381, 4200, 29741, 1543, 44, 4564, 52, 10215, 78, 11561, 254, 11561, 105, 16075, 27662, 36266, 17174, 40741, 242, 6303, 15789, 30052, 23141, 242, 21670, 1543, 50705], "temperature": 0, "avg_logprob": -0.10067456994353041, "compression_ratio": 1.191044776119403, "no_speech_prob": 1.7110691336030825e-11}, {"id": 3, "seek": 2580, "start": 32.6, "end": 42.400000000000006, "text": "在技術上,MinerU Popo採用4B參數後處理模型,並集合任務化數據引擎。動態分塊同步和文檔增強方法。", "tokens": [50705, 3581, 32502, 9890, 241, 5708, 11, 44, 4564, 52, 10215, 78, 6900, 94, 9254, 19, 33, 47375, 30622, 5661, 39289, 13876, 41908, 39823, 11, 35934, 26020, 14245, 26443, 39517, 23756, 30622, 36841, 41301, 13167, 236, 1543, 12572, 45248, 6627, 26268, 13089, 31429, 12565, 17174, 40741, 242, 24228, 252, 22752, 9249, 11148, 1543, 51195], "temperature": 0, "avg_logprob": -0.10067456994353041, "compression_ratio": 1.191044776119403, "no_speech_prob": 1.7110691336030825e-11}, {"id": 4, "seek": 2580, "start": 42.400000000000006, "end": 48.400000000000006, "text": "重點解決長文檔在分翼、跨翼和複雜版式下容易出現的結構斷裂問題。", "tokens": [51195, 12624, 8216, 17278, 33540, 15353, 17174, 40741, 242, 3581, 6627, 18573, 120, 1231, 6563, 101, 18573, 120, 12565, 164, 97, 229, 6306, 250, 42096, 27584, 4438, 49212, 7781, 9581, 1546, 17144, 43362, 4307, 115, 8083, 224, 17197, 1543, 51495], "temperature": 0, "avg_logprob": -0.10067456994353041, "compression_ratio": 1.191044776119403, "no_speech_prob": 1.7110691336030825e-11}, {"id": 5, "seek": 2580, "start": 48.400000000000006, "end": 55.400000000000006, "text": "在公開指標中,接入Popo框架後,MinerU的TEDS從53.7提升到90.6。", "tokens": [51495, 3581, 13545, 8949, 25922, 46299, 5975, 11, 14468, 14028, 38677, 78, 21416, 228, 7360, 114, 5661, 11, 44, 4564, 52, 1546, 51, 4731, 50, 21068, 19584, 13, 22, 20949, 41670, 4511, 7771, 13, 21, 1543, 51845], "temperature": 0, "avg_logprob": -0.10067456994353041, "compression_ratio": 1.191044776119403, "no_speech_prob": 1.7110691336030825e-11}, {"id": 6, "seek": 5540, "start": 55.4, "end": 62.4, "text": "MineQ-C2從48.9提升到87.4,說明它能夠顯著提升文檔結構恢復質量。", "tokens": [50365, 44, 533, 48, 12, 34, 17, 21068, 13318, 13, 24, 20949, 41670, 4511, 23853, 13, 19, 11, 4622, 11100, 11284, 8225, 31649, 46605, 19382, 20949, 41670, 17174, 40741, 242, 17144, 43362, 11845, 95, 2172, 102, 43450, 26748, 1543, 50715], "temperature": 0, "avg_logprob": -0.12722345079694475, "compression_ratio": 1.171003717472119, "no_speech_prob": 1.9842270188030753e-11}, {"id": 7, "seek": 5540, "start": 62.4, "end": 72.4, "text": "它的價值在於讓知識庫、RAG智能問答、學術論文解析和企業文檔治理,獲得更乾淨、更穩定、更可計算的文檔資產。", "tokens": [50715, 45224, 45441, 40242, 3581, 19488, 21195, 6498, 43143, 6346, 104, 1231, 3750, 38, 5094, 118, 8225, 11361, 28223, 1231, 21372, 9890, 241, 29340, 17174, 17278, 7360, 238, 12565, 7384, 223, 27119, 17174, 40741, 242, 30118, 13876, 11, 29057, 110, 5916, 19002, 39698, 14176, 101, 1231, 19002, 13740, 102, 12088, 1231, 19002, 4429, 30114, 19497, 1546, 17174, 40741, 242, 35380, 33299, 1543, 51215], "temperature": 0, "avg_logprob": -0.12722345079694475, "compression_ratio": 1.171003717472119, "no_speech_prob": 1.9842270188030753e-11}, {"id": 8, "seek": 5540, "start": 72.4, "end": 78.4, "text": "MinerU Popo讓複雜文檔從可識別,走向可理解、可治理、可計算。", "tokens": [51215, 44, 4564, 52, 10215, 78, 21195, 164, 97, 229, 6306, 250, 17174, 40741, 242, 21068, 4429, 43143, 16158, 11, 9575, 24282, 4429, 13876, 17278, 1231, 4429, 30118, 13876, 1231, 4429, 30114, 19497, 1543, 51515], "temperature": 0, "avg_logprob": -0.12722345079694475, "compression_ratio": 1.171003717472119, "no_speech_prob": 1.9842270188030753e-11}, {"id": 9, "seek": 7840, "start": 78.4, "end": 80.4, "text": "MinerU Popo", "tokens": [50365, 44, 4564, 52, 10215, 78, 50465], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 10, "seek": 7840, "start": 80.4, "end": 81.4, "text": "MinerU Popo", "tokens": [50465, 44, 4564, 52, 10215, 78, 50515], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 11, "seek": 7840, "start": 81.4, "end": 82.4, "text": "MinerU Popo", "tokens": [50515, 44, 4564, 52, 10215, 78, 50565], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 12, "seek": 7840, "start": 82.4, "end": 83.4, "text": "MinerU Popo", "tokens": [50565, 44, 4564, 52, 10215, 78, 50615], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 13, "seek": 7840, "start": 83.4, "end": 84.4, "text": "MinerU Popo", "tokens": [50615, 44, 4564, 52, 10215, 78, 50665], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 14, "seek": 7840, "start": 84.4, "end": 85.4, "text": "MinerU Popo", "tokens": [50665, 44, 4564, 52, 10215, 78, 50715], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 15, "seek": 7840, "start": 85.4, "end": 86.4, "text": "MinerU Popo", "tokens": [50715, 44, 4564, 52, 10215, 78, 50765], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 16, "seek": 7840, "start": 86.4, "end": 87.4, "text": "MinerU Popo", "tokens": [50765, 44, 4564, 52, 10215, 78, 50815], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 17, "seek": 7840, "start": 87.4, "end": 88.4, "text": "MinerU Popo", "tokens": [50815, 44, 4564, 52, 10215, 78, 50865], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 18, "seek": 7840, "start": 88.4, "end": 89.4, "text": "MinerU Popo", "tokens": [50865, 44, 4564, 52, 10215, 78, 50915], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 19, "seek": 7840, "start": 89.4, "end": 91.4, "text": "MinerU Popo", "tokens": [50915, 44, 4564, 52, 10215, 78, 51015], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 20, "seek": 7840, "start": 91.4, "end": 92.4, "text": "MinerU Popo", "tokens": [51015, 44, 4564, 52, 10215, 78, 51065], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 21, "seek": 7840, "start": 92.4, "end": 93.4, "text": "MinerU Popo", "tokens": [51065, 44, 4564, 52, 10215, 78, 51115], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 22, "seek": 7840, "start": 93.4, "end": 94.4, "text": "MinerU Popo", "tokens": [51115, 44, 4564, 52, 10215, 78, 51165], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 23, "seek": 7840, "start": 94.4, "end": 95.4, "text": "MinerU Popo", "tokens": [51165, 44, 4564, 52, 10215, 78, 51215], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 24, "seek": 7840, "start": 95.4, "end": 96.4, "text": "MinerU Popo", "tokens": [51215, 44, 4564, 52, 10215, 78, 51265], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 25, "seek": 7840, "start": 96.4, "end": 97.4, "text": "MinerU Popo", "tokens": [51265, 44, 4564, 52, 10215, 78, 51315], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 26, "seek": 7840, "start": 97.4, "end": 98.4, "text": "MinerU Popo", "tokens": [51315, 44, 4564, 52, 10215, 78, 51365], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 27, "seek": 7840, "start": 98.4, "end": 99.4, "text": "MinerU Popo", "tokens": [51365, 44, 4564, 52, 10215, 78, 51415], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 28, "seek": 7840, "start": 99.4, "end": 100.4, "text": "MinerU Popo", "tokens": [51415, 44, 4564, 52, 10215, 78, 51465], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 29, "seek": 7840, "start": 100.4, "end": 101.4, "text": "MinerU Popo", "tokens": [51465, 44, 4564, 52, 10215, 78, 51515], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 30, "seek": 7840, "start": 101.4, "end": 102.4, "text": "MinerU Popo", "tokens": [51515, 44, 4564, 52, 10215, 78, 51565], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 31, "seek": 7840, "start": 102.4, "end": 103.4, "text": "MinerU Popo", "tokens": [51565, 44, 4564, 52, 10215, 78, 51615], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 32, "seek": 7840, "start": 103.4, "end": 104.4, "text": "MinerU Popo", "tokens": [51615, 44, 4564, 52, 10215, 78, 51665], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 33, "seek": 7840, "start": 104.4, "end": 105.4, "text": "MinerU Popo", "tokens": [51665, 44, 4564, 52, 10215, 78, 51715], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}, {"id": 34, "seek": 7840, "start": 105.4, "end": 106.4, "text": "MinerU Popo", "tokens": [51715, 44, 4564, 52, 10215, 78, 51765], "temperature": 0, "avg_logprob": -0.17050259009651517, "compression_ratio": 12.434782608695652, "no_speech_prob": 1.3218524053115743e-09}], "language": "zh"}